© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31544
    Prev
    Next
    INDEX
    Explanations

    past tense verbs or dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .bio
    -0.13
    alyze
    -0.11
    iec
    -0.10
     crisp
    -0.10
    iez
    -0.10
     indust
    -0.10
     Besch
    -0.10
    utar
    -0.10
    meld
    -0.10
    cec
    -0.09
    POSITIVE LOGITS
    iko
    0.07
    _mE
    0.07
    edImage
    0.06
     hereby
    0.06
     Mystic
    0.06
    <x
    0.06
    aje
    0.06
    aque
    0.06
    sock
    0.06
     ASC
    0.06
    Activations Density 3.135%

    No Known Activations